Oil, Gas & Energy

Vantage connects to SCADA historians, reservoir engineering databases, and ERP systems to give energy operators real-time visibility into production performance, equipment health, and regulatory compliance. Build control room dashboards, automate state regulatory reporting, and apply AI to predict production decline and detect operational anomalies.

Surveil Production and Analyze Decline Curves

Monitor wellhead production in real time, compare against forecasted decline curves, and flag underperformers.

Scenario: A production engineering team managing 200 wells across three fields needs hourly production surveillance with automated detection of wells producing below their decline curve forecast.

Workflow Steps:

1. Schedule Trigger — Run every hour during production
2. Database Query (PostgreSQL) — Pull wellhead flow rates from the SCADA historian: well ID, oil rate (BOPD), gas rate (MCFD), water rate (BWPD), tubing pressure (psi), casing pressure (psi), choke size
3. Database Query (MSSQL) — Pull decline curve parameters and production targets from the reservoir engineering database: well ID, initial rate, decline rate (%), decline type (exponential/hyperbolic), monthly target
4. Join — Merge actual production with forecasted production on well ID
5. Computed Column — Calculate performance metrics:
   • Production variance: (actual_rate - forecasted_rate) / forecasted_rate * 100
   • Water cut: water_rate / (oil_rate + water_rate) * 100
   • Gas-oil ratio: gas_rate / oil_rate
   • Flowing wellhead pressure gradient: change from previous reading
6. Filter — Flag wells meeting any exception criteria:
   • Production > 10% below forecast
   • Water cut increased > 5% from 30-day average
   • Abnormal pressure changes (> 2σ from rolling average)
   • Gas-oil ratio spike (possible gas breakthrough)
7. AI Enrichment — For each flagged well, correlate with operational context and classify probable root cause:
   • Mechanical: pump failure, tubing leak, rod part, gas lock
   • Reservoir: water coning, natural decline exceeding model, offset well interference
   • Surface: choke change, separator backpressure, pipeline restriction
   • Weather/environmental: freeze-off, lightning strike, flooding
8. Multi-Conditional — Route by root cause classification:
   • Mechanical → Create Issue (Jira) for field maintenance crew with well ID, symptoms, and recommended diagnostics + Send Message (Slack #field-ops) + Dashboard Output
   • Reservoir → Dashboard Output to Predictive Insights Tile for reservoir engineer review + Send Email to subsurface team lead
   • Surface → Send Message (Slack) to field superintendent with recommended action
   • Weather → Dashboard Output for logging (no human action needed)
9. Dashboard Output — Populate:
   • Line Tile — Production rate trends per well/lease with decline curve overlay
   • Map Tile — Well locations color-coded by status (producing, shut-in, flagged, offline)
   • Forecast Tile — 12-month production projection with P10/P50/P90 confidence bands
   • Metric Tile — Field-level: total BOE/day, LOE/BOE, water cut %, uptime %
   • Scatter Tile — Actual vs. forecasted production (every well as a point; below the line = underperforming)
   • Table Tile — Exception list: flagged wells with root cause and recommended action
   • Predictive Insights Tile — AI-predicted production decline for the next 6 months
10. Write CSV — Export daily production allocation volumes for state regulatory reporting (Texas RRC Form PR, NDIC, WOGCC)

Key Nodes: Schedule Trigger, Database Query (PostgreSQL, MSSQL), Join, Computed Column, Filter, AI Enrichment, Multi-Conditional, Create Issue (Jira), Write CSV, Dashboard Output, Send Email, Send Message

Track Emissions and Maintain Environmental Compliance

Aggregate emissions data, evaluate against EPA thresholds, and automate regulatory report generation.

Scenario: An operator must track and report greenhouse gas emissions from flaring, venting, fugitive sources, and fuel combustion equipment across 15 facilities — in compliance with EPA Subpart W and NSPS OOOOa/OOOOb.

Workflow Steps:

1. Schedule Trigger — Run daily at midnight
2. Database Query (PostgreSQL) — Pull emissions source data:
   • Flare volumes (MCF) and combustion efficiency from flare meters
   • Tank battery emissions estimates (flash gas calculations)
   • Compressor engine fuel consumption (MCF)
   • Pneumatic device counts and bleed rates
3. Database Query (MSSQL) — Pull fugitive emission survey results: component counts, leak detections, repair dates
4. Aggregation — Sum emissions by source category and facility:
   • Flaring: MCF × emission factor → metric tons CO2e
   • Venting: estimated volumes × GWP of methane
   • Fugitive: leak rate × duration × emission factor
   • Combustion: fuel consumption × equipment-specific factor
5. Computed Column — Calculate:
   • Total facility emissions (metric tons CO2e)
   • Emissions intensity: total_emissions / total_BOE_produced
   • Year-to-date cumulative emissions
   • Projected annual emissions (run rate)
6. AI Compliance Check — Evaluate against regulatory thresholds:
   • EPA Subpart W: 25,000 metric tons CO2e annual reporting threshold
   • NSPS OOOOa/OOOOb: component-level monitoring and repair requirements
   • State-specific rules: flare limits, venting restrictions, reporting deadlines
7. Multi-Conditional — Route exceedances:
   • Threshold exceeded or projected to exceed → Send Email to HSE manager + Send Email to environmental compliance officer + Dashboard Output (Event Monitor Tile)
   • Approaching threshold (> 80% of limit) → Send Message (Slack #environmental) + Dashboard Output (warning)
   • Below threshold → Dashboard Output only
8. Dashboard Output — Populate:
   • Bar Tile — Emissions by source category (stacked: flaring, venting, fugitive, combustion)
   • Line Tile — Monthly emissions trend with regulatory threshold line
   • Comparison Tile — Year-over-year emissions intensity per BOE
   • Map Tile — Facility locations sized by total emissions
   • Event Monitor Tile — Real-time exceedance alerts
   • Metric Tile — Total CO2e, emissions intensity, LDAR compliance rate %
9. Write PDF — Generate monthly environmental compliance summary for management review and regulatory submission preparation
10. Write Excel — Archive detailed calculation workbook for auditor review

Key Nodes: Schedule Trigger, Database Query (PostgreSQL, MSSQL), Aggregation, Computed Column, AI Compliance Check, Multi-Conditional, Write PDF, Write Excel, Send Email, Send Message, Dashboard Output

Optimize Lease Operating Expenses Across the Portfolio

Monitor operating costs per lease, identify cost drivers, and benchmark against peers.

Scenario: A production manager running 80 leases needs to track LOE on a per-BOE basis, identify leases with escalating costs, and optimize well workovers by cost–benefit analysis.

Workflow Steps:

1. Schedule Trigger — Run weekly
2. Database Query (MSSQL) — Pull monthly operating expenses from the ERP: lease, AFE number, cost category (labor, chemicals, power, repairs, water disposal), amount
3. Database Query (PostgreSQL) — Pull monthly production volumes from the production database: lease, oil, gas, water, BOE
4. Join — Merge costs with production on lease and period
5. Computed Column — Calculate LOE metrics:
   • Total LOE per lease
   • LOE per BOE: total_costs / total_BOE
   • Cost breakdown as % of total: labor %, power %, chemicals %, etc.
   • Month-over-month cost change %
6. Aggregation — Roll up by field, by cost category, and by operator (if multiple operators)
7. Sort — Leases with highest LOE/BOE first
8. Filter — Leases where LOE/BOE exceeds the field average by > 25% or month-over-month cost increase > 15%
9. AI Enrichment — Analyze cost drivers for each flagged lease: "Lease WX-14 LOE increased 32% MoM to $18.40/BOE. Primary driver: water disposal costs ($6,200/month, up from $3,800). Probable cause: increasing water cut from 65% to 78%. Recommend evaluating produced water recycling or disposal well drilling."
10. Dashboard Output — Populate:
    • Table Tile — Lease operating cost report with LOE/BOE and trend
    • Bar Tile — LOE by cost category across all leases
    • Scatter Tile —LOE/BOE vs. production rate (identify high-cost/low-production candidates for P&A)
    • Line Tile — LOE trend over 24 months by field
    • Comparison Tile — LOE/BOE this year vs. last year
    • Metric Tile — Company-wide LOE/BOE with sparkline
11. Write Excel — Generate the monthly LOE report for financial review
12. Send Email — Distribute to operations VP and accounting

Key Nodes: Schedule Trigger, Database Query (MSSQL, PostgreSQL), Join, Computed Column, Aggregation, Sort, Filter, AI Enrichment, Write Excel, Send Email, Dashboard Output

Manage Well Workovers and Capital Programs End to End

Track capital project approvals, workover schedules, and estimated vs. actual costs.

Scenario: A capital planning team manages 50+ workover AFEs (Authorizations for Expenditure) annually. They need to track AFE status, compare estimated vs. actual costs, and forecast remaining capital budget.

Workflow Steps:

1. Schedule Trigger — Run daily
2. Database Query (MSSQL) — Pull AFE records: AFE number, well ID, description, estimated cost, actual cost to date, status (proposed, approved, in-progress, complete), start date, completion date
3. Database Query (PostgreSQL) — Pull pre/post workover production data for completed workovers: 30-day avg before vs. 30-day avg after
4. Join — Merge AFE data with production lift data
5. Computed Column — Calculate:
   • Cost variance: (actual - estimated) / estimated * 100
   • Incremental production: post-workover rate - pre-workover rate
   • Payout period: actual_cost / (incremental_production * oil_price / 365) days
   • ROI: (incremental_annual_revenue - actual_cost) / actual_cost * 100
6. Aggregation — Summarize capital program:
   • Total budget, total spent, remaining
   • Average cost variance (are we over or under budget?)
   • Average incremental production lift per workover type
7. Multi-Conditional — Route by status:
   • AFE > 15% over budget → Send Email to operations VP + Dashboard Output (alert)
   • In-progress AFE > 30 days past scheduled completion → Send Message (Slack) to project manager
8. Dashboard Output — Populate:
   • Gantt Tile — AFE schedule: planned start/end vs. actual
   • Waterfall Tile — Total budget → approved → spent → remaining → projected overrun
   • Table Tile — AFE detail with variance and ROI
   • Scatter Tile — Workover cost vs. incremental production (ROI visualization)
   • Metric Tile — Capital spent / budget, average workover ROI, average payout period
   • Forecast Tile — Projected capital spend through year-end based on AFE schedule

Key Nodes: Schedule Trigger, Database Query (MSSQL, PostgreSQL), Join, Computed Column, Aggregation, Multi-Conditional, Send Email, Send Message, Dashboard Output

Example Dashboard: Production & Asset Operations Center

Build this dashboard to give your operations team real-time visibility into well performance, production status, environmental compliance, and capital project tracking.

Row 1 — Production Overview

Row 2 — Field Operations

Row 3 — Performance & Forecasting

Row 4 — Environmental & Economics

Row 5 — Capital & Compliance

Getting Started

To build energy operations workflows:

1. Connect your data sources — Add your SCADA historian (PostgreSQL), reservoir engineering database, and ERP (MSSQL) under Integrations
2. Start with production monitoring — Build an hourly Schedule Trigger → Database Query → Join → Dashboard Output workflow
3. Add exception detection — Use Filter + AI Enrichment to flag underperforming wells and classify root causes
4. Automate regulatory reporting — AI Compliance Check for emissions thresholds, Write CSV/PDF for state filings
5. Build the control room — Map Tile, Line Tile, and Metric Tile provide at-a-glance field operations visibility